# Incremental Roseland: Batch-wise Landmark Diffusion via Kernelized Sequential Karhunen--Lo\`eve Update

> Source: <https://arxiv.org/abs/2611.23414>
> Published: 2026-11-19 05:00:00+00:00

**Key takeaway:** iRoseland updates the Roseland landmark-diffusion embedding in a single bounded-memory pass via a kernelized Sequential Karhunen-Loève scheme, matching Roseland to round-off on stationary data and beating equal-memory Roseland by an order of magnitude on long streams.

arXiv:2611.23414v1 Announce Type: new 
Abstract: Landmark diffusion (Roseland) computes a diffusion-map-style spectral embedding from the singular value decomposition of a degree-normalized data-to-landmark kernel matrix, at a cost far below that of full diffusion maps. It assumes, however, that all data are available at once. We introduce incremental Roseland (iRoseland), which casts the landmark affinity as a row-growing matrix whose SVD can be updated with a kernelized Sequential Karhunen--Lo\`eve (SKL) scheme. Degre correction is handled by a first order expansion about a reference mean kernel row and so that the landmark-side eigenbasis may be recovered from a single landmark-by-landmark eigendecomposition at each step. The presented method requires only a single pass over the data and runs in bounded-memory with state independent of the number of points processed. A forgetting factor lets the method track drifting distributions, and a sample-size-invariant embedding keeps outputs comparable across time. Experiments show agreement with Roseland to round-off on stationary data, and accuracy that exceeds equal-memory Roseland by an order of magnitude on long streams. On drifting data, we observe large gains from forgetting with a window matched to the drift.
